bert-goemotions-15epochs-run2 – AI Model by mpalaval | AlphaNeural AI

You can deploy this model and start earning money today!

mpalaval/
bert-goemotions-15epochs-run2

like

0

generated_from_trainer

google-bert/bert-base-cased

endpoints_compatible

Views

No views yet

bert-goemotions-15epochs-run2

This model is a fine-tuned version of bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.1154
Accuracy Thresh: 0.9616
F1 weighted: 0.3672
F1 macro: 0.2835
Accuracy: 0.4083
Recall weighted: 0.4083
Recall macro: 0.2851

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 15
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy Thresh	F1 weighted	F1 macro	Accuracy	Recall weighted	Recall macro
0.1322	1.0	5283	0.1205	0.9609	0.3371	0.2432	0.3944	0.3944	0.2539
0.1189	2.0	10566	0.1165	0.9614	0.3573	0.2726	0.4062	0.4062	0.2835
0.114	3.0	15849	0.1154	0.9616	0.3672	0.2835	0.4083	0.4083	0.2851
0.1098	4.0	21132	0.1157	0.9613	0.3743	0.2929	0.4019	0.4019	0.2996
0.1059	5.0	26415	0.1172	0.9609	0.3751	0.2959	0.4002	0.4002	0.3049
0.1023	6.0	31698	0.1173	0.9610	0.3779	0.3012	0.3986	0.3986	0.3135
0.0988	7.0	36981	0.1188	0.9603	0.3805	0.3082	0.3925	0.3925	0.3175
0.0956	8.0	42264	0.1199	0.9601	0.3803	0.3044	0.3973	0.3973	0.3129

Framework versions

Transformers 4.35.1
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1